CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-22 12:27:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add Q4_3 support to cuBLAS (#1086)

Browse Source
This commit is contained in:
slaren
2023-04-20 20:49:53 +02:00
committed by GitHub
parent 8a1756abdf
commit 2005469ea1
3 changed files with 41 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Makefile
View File

@@ -102,7 +102,7 @@ ifdef LLAMA_OPENBLAS
endif
ifdef LLAMA_CUBLAS
CFLAGS += -DGGML_USE_CUBLAS -I/usr/local/cuda/include
LDFLAGS += -lcublas_static -lculibos -lcudart_static -lcublasLt_static -lpthread -ldl -lrt -L/usr/local/cuda/lib64
LDFLAGS += -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64
OBJS += ggml-cuda.o
ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
nvcc -arch=native -c -o $@ $<